© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 13420
    Prev
    Next
    INDEX
    Explanations

    markdown table headers or features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     for
    0.59
     genotype
    0.46
    椏
    0.45
     chock
    0.45
     five
    0.44
     three
    0.44
     subscript
    0.44
     typing
    0.44
     from
    0.43
     axles
    0.43
    POSITIVE LOGITS
    ，
    0.64
    Также
    0.54
     также
    0.52
     również
    0.52
    <h2>
    0.51
    ،
    0.51
     myös
    0.50
     zudem
    0.50
     как
    0.50
     jika
    0.50
    Activations Density 0.234%

    No Known Activations